INDEX

Explanations

terms related to health care, specifically focusing on demographics and quality indicators

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Abbreviations and acronyms

np_acts-logits-general · gemini-2.0-flash

specific terms followed by defining nouns

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.65

。

-0.50

-0.49

人了

-0.47

 ujednoznacz

-0.44

$.

-0.41

".

-0.41

 respectivamente

-0.40

++.

-0.40

POSITIVE LOGITS

is

1.31

has

1.19

들은

1.13

리는

1.06

isn

1.06

에는

1.04

may

1.04

 doesn

1.00

 tends

1.00

지는

0.99

Activations Density 1.952%

terms related to health care, specifically focusing on demographics and quality indicators

Abbreviations and acronyms

specific terms followed by defining nouns

No Comments

No Known Activations